Human activity recognition making use of long short-term memory techniques

WAINWRIGHT, Richard and SHENFIELD, Alex (2019). Human activity recognition making use of long short-term memory techniques. Athens Journal of Sciences, 6 (1), 19-34.

2018-2548-AJS-ELE-Wainwright-03.pdf - Published Version
Creative Commons Attribution Non-commercial.

Download (598kB) | Preview
Official URL:
Open Access URL: (Published)


The optimisation and validation of a classifiers performance when applied to real world problems is not always effectively shown. In much of the literature describing the application of artificial neural network architectures to Human Activity Recognition (HAR) problems, postural transitions are grouped together and treated as a singular class. This paper proposes, investigates and validates the development of an optimised artificial neural network based on Long-Short Term Memory techniques (LSTM), with repeated cross validation used to validate the performance of the classifier. The results of the optimised LSTM classifier are comparable or better to that of previous research making use of the same dataset, achieving 95% accuracy under repeated 10-fold cross validation using grouped postural transitions. The work in this paper also achieves 94% accuracy under repeated 10-fold cross validation whilst treating each common postural transition as a separate class (and thus providing more context to each activity).

Item Type: Article
Additional Information: Presented at the 2nd Annual International Conference on Electrical Engineering - A Stream on “Data Science”
Identification Number:
Page Range: 19-34
SWORD Depositor: Symplectic Elements
Depositing User: Symplectic Elements
Date Deposited: 26 Feb 2019 15:03
Last Modified: 18 Mar 2021 01:46

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics